Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
0 benchmarks in common.
4 models selected. 0 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | OpenAI | Qwen | Anthropic | Anthropic |
|---|---|---|---|---|
| Arena ELOHuman preference | Not in our dataset | 1,336 | 1,388 | 1,455 |
| LiveBench 1.0General reasoning | Not in our dataset | 72.0% | Not in our dataset | Not in our dataset |
| GPQA DiamondScientific knowledge | 71.5% | 65.6% | 78.2% | Not in our dataset |
| HLEAcademic reasoning | Not in our dataset | Not in our dataset | 8.0% | 7.5% |
| MMLU ProMulti-task understanding | 74.8% | Not in our dataset | Not in our dataset | Not in our dataset |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | 46.4% | Not in our dataset |
| AIME 2025Mathematics | Not in our dataset | 69.5% | Not in our dataset | Not in our dataset |
| AiderCode editing | Not in our dataset | 20.9% | 64.9% | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | Not in our dataset | 62.3% | Not in our dataset |
| LiveCodeBenchCompetitive coding | Not in our dataset | 62.7% | Not in our dataset | Not in our dataset |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | 81.2% | Not in our dataset |
| Terminal-BenchAgentic terminal | Not in our dataset | Not in our dataset | Not in our dataset | 42.8% |
| ARC-AGI-2Visual reasoning | Not in our dataset | Not in our dataset | 0.7% | 3.8% |
Pricing & context Published USD rates per 1M tokens
| Specification | GPT-OSS 20B Thinking | QwQ 32B Thinking | Claude 3 Sonnet 3.7 Thinking | Claude Sonnet 4 4.5 Non-thinking |
|---|---|---|---|---|
| Input | $0.024 | $0.2 | $3 | $3 |
| Output | $0.112 | $0.2 | $15 | $15 |
| Context window | 131K | 33K | 200K | 1.0M |
| Pricing details | Explore pricing → | Explore pricing → | Explore pricing → | Explore pricing → |
How to read this comparison
Each column keeps the exact model version you selected. Shared benchmarks are the intersection of their reported results; “all coverage” also shows where evidence is missing. Missing results never count as zero.
These are published benchmark scores, not a controlled head-to-head test. The available evidence does not establish matching evaluation settings, so we show no cross-model winner highlights or deltas. Composite quality scores are omitted because they can summarize different benchmark sets.
Scores and statistics are computed upstream. This page reads a fixed data snapshot; its date describes the snapshot, not the date of every measurement.